作者位次 #4/6ICLR 2026Poster· Computer Vision / Vision Models & Multimodal
What "Not" to Detect: Negation-Aware VLMs via Structured Reasoning and Token Merging
Inha Kang · Youngsun Lim · Seonho Lee · Jiho Choi · Junsuk Choe · Hyunjung Shim
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Inha Kang · Youngsun Lim · Seonho Lee · Jiho Choi · Junsuk Choe · Hyunjung Shim
Jiho Choi · Seojeong Park · Seongjong Song · Hyunjung Shim
Automating scientific poster generation requires hierarchical document understanding and coherent content-layout planning.Existing methods often rely on flat summarization or optimize content and layout separately.As a result, they often suffer from information loss, weak logical flow, and poor v...